2025

• Approximate Thompson sampling for learning linear quadratic regulators with $O(\sqrt{T})$ regret

  Yeoneung Kim, Gihun Kim, Jiwhan Park, and Insoon Yang

  Learning for Dynamics and Control (L4DC), 2025. (Oral)

• Egocentric conformal prediction for safe and efficient navigation in dynamic cluttered environments

  Jaeuk Shin, Jungjin Lee, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2025.

• On the steady-state distributionally robust Kalman filter

  Minhyuk Jang, Astghik Hakobyan, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2025.

• Robust continuous-time generation scheduling under power demand uncertainty: An affine decision rule approach

  Youngchae Cho, Insoon Yang, and Takayuki Ishizaki

  IEEE Conference on Decision and Control (CDC), 2025.

2024

• Wasserstein distributionally robust control of partially observable linear stochastic systems

  Astghik Hakobyan, and Insoon Yang

  IEEE Transactions on Automatic Control, 69(9):6121–6136, 2024.

• Risk-aware Wasserstein distributionally robust control of vessels in natural waterways

  Juan Moreno Nadales, Astghik Hakobyan, David Munoz de la Pena, Daniel Limon, and Insoon Yang

  IEEE Transactions on Control Systems Technology, 32(4):1471–1478, 2024.

• On task-relevant loss functions in meta-reinforcement learning

  Jaeuk Shin, Giho Kim, Howon Lee, Joonho Han, and Insoon Yang

  Learning for Dynamics and Control (L4DC), 2024.

• Multiparametric analysis of multi-task Markov decision processes: Structure, invariance, and reducibility

  Jaeuk Shin, and Insoon Yang

  IEEE Control Systems Letters, 8:928–933, 2024. (Selected for presentation at CDC'24)

• Wasserstein distributionally robust regret minimization

  Youngchae Cho, and Insoon Yang

  IEEE Control Systems Letters, 8:820–825, 2024. (Selected for presentation at CDC'24)

• Anderson acceleration for partially observable Markov decision processes: A maximum entropy approach

  Mingyu Park, Jaeuk Shin, and Insoon Yang

  Automatica, 163:111557, 2024.

• Control of fab lifters via deep reinforcement learning: A semi-MDP approach

  Giho Kim, Jaeuk Shin, Gihun Kim, Joonrak Kim, and Insoon Yang

  IEEE Transactions on Automation Science and Engineering, 21(4):5136–5148, 2024.

2023

• Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels

  Jungbin Kim, and Insoon Yang

  Advances in Neural Information Processing Systems (NeurIPS), 2023.

• Distributionally robust differential dynamic programming with Wasserstein distance

  Astghik Hakobyan, and Insoon Yang

  IEEE Control Systems Letters, 7:2329–2334, 2023. (Selected for presentation at CDC'23)

• Data-driven stochastic optimization using upper confidence bounds: Performance guarantees and distributional robustness

  Youngchae Cho, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2023.

• On concentration bounds for Bayesian identification of linear non-Gaussian systems

  Yeoneung Kim, Gihun Kim, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2023.

• Unifying Nesterov’s accelerated gradient methods for convex and strongly convex objective functions

  Jungbin Kim, and Insoon Yang

  International Conference on Machine Learning (ICML), 2023. (Oral, top 2%)

• Distributionally robust optimization with unscented transform for learning-based motion control in dynamic environments

  Astghik Hakobyan, and Insoon Yang

  IEEE International Conference on Robotics and Automation (ICRA), 2023.

• Maximum entropy optimal control of continuous-time dynamical systems

  Jeongho Kim, and Insoon Yang

  IEEE Transactions on Automatic Control, 68(4):2018–2033, 2023.

• Distributional robustness in minimax linear quadratic control with Wasserstein distance

  Kihyun Kim, and Insoon Yang

  SIAM Journal on Control and Optimization, 61(2):458-483, 2023.

• Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach

  Astghik Hakobyan, and Insoon Yang

  IEEE Transactions on Robotics, 39(1):718-737, 2023.

2022

• Improved regret analysis for variance-adaptive linear bandits and horizon-free linear mixture MDPs

  Yeoneung Kim, Insoon Yang, and Kwang-Sung Jun

  Advances in Neural Information Processing Systems (NeurIPS), 2022.

• Wasserstein distributionally robust control of partially observable linear systems: Tractable approximation and performance guarantee

  Astghik Hakobyan, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2022.

• On affine policies for Wasserstein distributionally robust unit commitment

  Youngchae Cho, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2022.

• Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments

  Jaeuk Shin, Astghik Hakobyan, Mingyu Park, Yeoneung Kim, Gihun Kim, and Insoon Yang

  IEEE Robotics and Automation Letters, 7(4):10065–10072, 2022. (Selected for presentation at IROS'22)

• On representation formulas for optimal control: A Lagrangian perspective

  Yeoneung Kim, and Insoon Yang

  IET Control Theory & Applications, 16(16):1633-1644, 2022.

• Accelerated gradient methods for geodesically convex optimization: Tractable algorithms and convergence analysis

  Jungbin Kim, and Insoon Yang

  International Conference on Machine Learning (ICML), 2022.

• Risk-sensitive safety analysis using conditional value-at-risk

  Margaret P. Chapman, Riccardo Bonalli, Kevin M. Smith, Insoon Yang, Marco Pavone, and Claire J. Tomlin

  IEEE Transactions on Automatic Control, 67(12):6521-6536, 2022.

• Wasserstein distributionally robust motion control for collision avoidance using conditional value-at-risk

  Astghik Hakobyan, and Insoon Yang

  IEEE Transactions on Robotics, 38(2):939–957, 2022.

• Stochastic consensus dynamics for nonconvex optimization on the Stiefel manifold: Mean-field limit and convergence

  Seung-Yeal Ha, Myeongju Kang, Dohyun Kim, Jeongho Kim, and Insoon Yang

  Mathematical Models and Methods in Applied Sciences, 32(3):533–617, 2022.

2021

• Hamilton-Jacobi deep Q-learning for deterministic continuous-time systems with Lipschitz continuous controls

  Jeongho Kim, Jaeuk Shin, and Insoon Yang

  Journal of Machine Learning Research (JMLR), 22(206):1–34, 2021.

• Wasserstein distributionally robust stochastic control: A data-driven approach

  Insoon Yang

  IEEE Transactions on Automatic Control, 66(8):3863–3870, 2021.

• Appropriate Smart Factory for SMEs: Concept, Application and Perspective

  Woo-Kyun Jung, Dong-Ryul Kim, Hyunsu Lee, Tae-Hun Lee, Insoon Yang, Byeng D. Youn, Daniel Zontar, Matthias Brockmann, Christian Brecher, and Sung-Hoon Ahn

  International Journal of Precision Engineering and Manufacturing, 22:201–215, 2021.

• On Anderson acceleration for partially observable Markov decision processes

  Melike Ermis, Mingyu Park, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2021.

• Toward improving the distributional robustness of risk-aware controllers in learning-enabled environments

  Astghik Hakobyan, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2021.

2020

• A convex optimization approach to dynamic programming in continuous state and action spaces

  Insoon Yang

  Journal of Optimization Theory and Applications (JOTA), 187:133–157, 2020.

• Multi-objective predictive taxi dispatch via network flow optimization

  Beomjun Kim, Jeongho Kim, Subin Huh, Seungil You, and Insoon Yang

  IEEE Access, 8:21437–21452, 2020.

• A3DQN: Adaptive Anderson acceleration for deep Q-networks

  Melike Ermis, and Insoon Yang

  IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 250–257, 2020.

• Minimax control of ambiguous linear stochastic systems using the Wasserstein metric

  Kihyun Kim, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2020.

• A stochastic consensus method for nonconvex optimization on the Stiefel manifold

  Jeongho Kim, Myeongju Kang, Dohyun Kim, Seung-Yeal Ha, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2020.

• Learning-based distributionally robust motion control with Gaussian processes

  Astghik Hakobyan, and Insoon Yang

  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020.

• Hamilton-Jacobi-Bellman equations for Q-learning in continuous time

  Jeongho Kim, and Insoon Yang

  Learning for Dynamics and Control (L4DC), 2020.

• Wasserstein distributionally robust motion planning and control with safety constraints using CVaR

  Astghik Hakobyan, and Insoon Yang

  IEEE International Conference on Robotics and Automation (ICRA), 490–496, 2020.

2019

• Submodularity of storage placement optimization in power networks

  Junjie Qin, Insoon Yang, and Ram Rajagopal

  IEEE Transactions on Automatic Control, 64(8):3268–3283, 2019. (Conference version selected as Best Student Paper Award finalist at CDC'16)

• Risk-aware motion planning and control using CVaR-constrained optimization

  Astghik Hakobyan, Gyeong Chan Kim, and Insoon Yang

  IEEE Robotics and Automation Letters, 4(4):3924–3931, 2019. (Selected for presentation at IROS'19)

• Sample efficient home power anomaly detection in real time using semi-supervised learning

  Xinlin Wang, Insoon Yang, and Sung-Hoon Ahn

  IEEE Access, 7:139712–139725, 2019.

• Stochastic subgradient methods for dynamic programming in continuous state and action spaces

  Sunho Jang, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2019.

• On improving the robustness of reinforcement learning-based controllers using disturbance observer

  Jeong Woo Kim, Hyungbo Shim, and Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2019.

2018

• A dynamic game approach to distributionally robust safety specifications for stochastic systems

  Insoon Yang

  Automatica, 94:94–101, 2018.

• Smart machining process using machine learning: A review and perspective on machining industry

  Dong-Hyeon Kim et al., and Insoon Yang

  International Journal of Precision Engineering and Manufacturing-Green Technology, 5(4):555–568, 2018. (IJPEM-GT Most Cited Article Award, 2020)

• Safety-aware optimal control of stochastic systems using conditional value-at-risk

  Samantha Samuelson, and Insoon Yang

  American Control Conference (ACC), 6285–6290, 2018.

2017

• Optimal control of conditional value-at-risk in continuous time

  Christopher W. Miller, and Insoon Yang

  SIAM Journal on Control and Optimization, 55(2):856–884, 2017.

• A convex optimization approach to distributionally robust Markov decision processes with Wasserstein distance

  Insoon Yang

  IEEE Control Systems Letters, 1(1):164–169, 2017. (Selected for presentation at CDC'17)

• Variance-constrained risk sharing in stochastic systems

  Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin

  IEEE Transactions on Automatic Control, 62(4):1865–1879, 2017.

• Distributionally robust stochastic control with conic confidence sets

  Insoon Yang

  IEEE Conference on Decision and Control (CDC), 2017.

• Data-driven distributionally robust control of energy storage to manage wind power fluctuations

  Samantha Samuelson, and Insoon Yang

  IEEE Conference on Control Technology and Applications (CCTA), 2017.

• Online combinatorial optimization for interconnected refrigeration systems: Linear approximation and submodularity

  Insoon Yang

  IFAC World Congress, 2017.

2016

• Approximation algorithms for optimization of combinatorial dynamical systems

  Insoon Yang, Samuel A. Burden, Ram Rajagopal, S. Shankar Sastry, and Claire J. Tomlin

  IEEE Transactions on Automatic Control, 61(9):2644–2649, 2016.

• Submodularity of energy storage placement in power networks

  Junjie Qin, Insoon Yang, and Ram Rajagopal

  IEEE Conference on Decision and Control (CDC), 2016. (Best Student Paper Award finalist)

• Reducing electricity price volatility via stochastic storage control

  Insoon Yang, and Asuman E. Ozdaglar

  American Control Conference (ACC), 2016.

~2015

• Indirect load control for financial risk management in electricity markets via risk-limiting dynamic contracts

  Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin

  American Control Conference (ACC), 2015.

• Utility learning model predictive control for personal electric loads

  Insoon Yang, Melanie N. Zeilinger, and Claire J. Tomlin

  IEEE Conference on Decision and Control (CDC), 2014.

• Reaction-diffusion systems in protein networks: Global existence and identification

  Insoon Yang, and Claire J. Tomlin

  Systems & Control Letters, 74:50–57, 2014.

• Direct load control for electricity market risk management via risk-limiting dynamic contracts

  Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin

  Allerton Conference on Communication, Control, and Computing, 2014.

• Path integral formulation of stochastic optimal control with generalized costs

  Insoon Yang, Matthias Morzfeld, Claire J. Tomlin, and Alexandre J. Chorin

  IFAC World Congress, 2014.

• Dynamic contracts with partial observations: application to indirect load control

  Insoon Yang, Duncan S. Callaway, and Claire J. Tomlin

  American Control Conference (ACC), 2014.

• Infinitesimal interconnection variation in nonlinear networked systems

  Insoon Yang, Samuel A. Burden, S. Shankar Sastry, and Claire J. Tomlin

  IEEE Conference on Decision and Control (CDC), 2013.

• Regularization-based identification for level set equations

  Insoon Yang, and Claire J. Tomlin

  IEEE Conference on Decision and Control (CDC), 2013.

• Identification of surface tension in mean curvature flow

  Insoon Yang, and Claire J. Tomlin

  American Control Conference (ACC), 2013.

• One-shot computation of reachable sets for differential games

  Insoon Yang, Sabine Becker-Weimann, Mina J. Bissell, and Claire J. Tomlin

  ACM International Conference on Hybrid Systems: Computation and Control (HSCC), 2013.

• Micro ECM with ultrasonic vibrations using a semi-cylindrical tool

  Insoon Yang, Min Su Park, and Chong Nam Chu

  International Journal of Precision Engineering and Manufacturing, 10(2):5–10, 2009.